Instance-Based Learning of Span Representations: A Case Study through Named Entity Recognition

04/29/2020
by   Hiroki Ouchi, et al.
0

Interpretable rationales for model predictions play a critical role in practical applications. In this study, we develop models possessing interpretable inference process for structured prediction. Specifically, we present a method of instance-based learning that learns similarities between spans. At inference time, each span is assigned a class label based on its similar spans in the training set, where it is easy to understand how much each training instance contributes to the predictions. Through empirical analysis on named entity recognition, we demonstrate that our method enables to build models that have high interpretability without sacrificing performance.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/09/2020

Interpretability Analysis for Named Entity Recognition to Understand System Predictions and How They Can Improve

Named Entity Recognition systems achieve remarkable performance on domai...
research
09/28/2021

Instance-Based Neural Dependency Parsing

Interpretable rationales for model predictions are crucial in practical ...
research
11/08/2019

SEPT: Improving Scientific Named Entity Recognition with Span Representation

We introduce a new scientific named entity recognizer called SEPT, which...
research
06/02/2020

Embeddings of Label Components for Sequence Labeling: A Case Study of Fine-grained Named Entity Recognition

In general, the labels used in sequence labeling consist of different ty...
research
10/10/2022

A dynamic programming algorithm for span-based nested named-entity recognition in O(n^2)

Span-based nested named-entity recognition (NER) has a cubic-time comple...
research
01/24/2022

BTPK-based learning: An Interpretable Method for Named Entity Recognition

Named entity recognition (NER) is an essential task in natural language ...
research
12/20/2017

Adversarial Structured Prediction for Multivariate Measures

Many predicted structured objects (e.g., sequences, matchings, trees) ar...

Please sign up or login with your details

Forgot password? Click here to reset